orte-clean: fix bad username/uid usage, add orte-dvm

This fixes a mismatch between PS listing that returned
USERNAME but code was pruning based on UID.

This changes the OPAL_PS_FLAVOR_CHECK format to return
'uid' instead of 'user'.  (Note: Avoiding call to
getlogin_r() but assuming UID is uniform on system,
same assumption exists for session dir anyway.)

Note, still maintains behavior from man page for root
running orte-clean on node (kills all orteds).

Adds 'orte-dvm' to list of procnames that will be checked/killed.

Signed-off-by: Thomas Naughton <naughtont@ornl.gov>

config/opal_check_ps.m4

@@ -13,6 +13,7 @@ dnl                         All rights reserved.
 dnl Copyright (c) 2007      Sun Microsystems, Inc.  All rights reserved.
 dnl Copyright (c) 2008      Cisco Systems, Inc.  All rights reserved.
 dnl Copyright (c) 2014      Intel, Inc. All rights reserved.
+dnl Copyright (c) 2017      UT-Battelle, LLC. All rights reserved.
 dnl $COPYRIGHT$
 dnl
 dnl Additional copyrights may follow
@@ -30,11 +31,11 @@ PS_FLAVOR="unknown"
 ps -A -o fname > /dev/null 2>&1
 
 if test "$?" = "0"; then
-     PS_FLAVOR="ps -A -o fname,pid,user"
+     PS_FLAVOR="ps -A -o fname,pid,uid"
 else
      ps -A -o command > /dev/null 2>&1
      if test "$?" = "0"; then
-         PS_FLAVOR="ps -A -o command,pid,user"
+         PS_FLAVOR="ps -A -o command,pid,uid"
      fi
 fi
 AC_MSG_RESULT([$PS_FLAVOR])

orte/tools/orte-clean/orte-clean.c

@@ -17,6 +17,7 @@
  * Copyright (c) 2015      Research Organization for Information Science
  *                         and Technology (RIST). All rights reserved.
  * Copyright (c) 2015      Intel, Inc. All rights reserved.
+ * Copyright (c) 2017      UT-Battelle, LLC. All rights reserved.
  * $COPYRIGHT$
  *
  * Additional copyrights may follow
@@ -275,12 +276,10 @@ void kill_procs(void) {
      * This is the command that is used to get the information about
      * all the processes that are running.  The output looks like the
      * following:
-     * COMMAND    PID     USER
-     * tcsh     12556    rolfv
-     * ps       14424    rolfv
+     * COMMAND    PID     UID
+     * tcsh     12556    1000
+     * ps       14424    1000
      * etc.
-     * Currently, we do not make use of the USER field, but we may later
-     * on so we grab it also.
      */
 
     /*
@@ -301,7 +300,7 @@ void kill_procs(void) {
      */
     ortedpid = getppid();
 
-    /* get the name of the user */
+    /* get the userid of the user */
     uid = getuid();
     asprintf(&this_user, "%d", uid);
 
@@ -322,8 +321,7 @@ void kill_procs(void) {
     psfile = popen(command, "r");
     /*
      * Read the first line of the output.  We just throw it away
-     * as it is the header consisting of the words COMMAND, PID and
-     * USER.
+     * as it is the header consisting of the words COMMAND, PID and UID.
      */
     if (NULL == (inputline = orte_getline(psfile))) {
         free(this_user);
@@ -347,7 +345,7 @@ void kill_procs(void) {
         /* If the user is not us, and the user is not root, then skip
          * further checking.  If the user is root, then continue on as
          * we want root to kill off everybody. */
-        if ((0 != strcmp(user, this_user)) && (0 != strcmp("root", this_user))) {
+        if ((0 != strcmp(user, this_user)) && (0 != strcmp("0", this_user))) {
             /* not us */
             free(inputline);
             continue;
@@ -371,11 +369,13 @@ void kill_procs(void) {
          * proc is sometimes reported that way
          */
         if (0 == strncmp("orted", procname, strlen("orted")) ||
-            0 == strncmp("(orted)", procname, strlen("(orted)"))) {
+            0 == strncmp("(orted)", procname, strlen("(orted)")) ||
+            0 == strncmp("orte-dvm", procname, strlen("orte-dvm")) ||
+            0 == strncmp("(orte-dvm)", procname, strlen("(orte-dvm)"))) {
             if (procpid != ortedpid) {
                 if (orte_clean_globals.verbose) {
                     fprintf(stderr, "orte-clean: found potential rogue orted process"
-                            " (pid=%d,user=%s), sending SIGKILL...\n",
+                            " (pid=%d,uid=%s), sending SIGKILL...\n",
                             procpid, user);
                 }
                 /*
@@ -397,7 +397,7 @@ void kill_procs(void) {
             if (procpid != ortedpid) {
                 if (orte_clean_globals.verbose) {
                     fprintf(stderr, "orte-clean: found potential rogue orterun process"
-                            " (pid=%d,user=%s), sending SIGKILL...\n",
+                            " (pid=%d,uid=%s), sending SIGKILL...\n",
                             procpid, user);
 
                 }